Showing cs.CLShow all
3 papers · 1 filter
cs.CL2025
Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access
Xiang Hu, Jiaqi Leng, Jun Zhao +2
A key advantage of Recurrent Neural Networks (RNNs) over Transformers is their linear computational and space complexity enables faster training and inference for long sequences. H…
cs.CL2025
Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English
Haoyang Zhang, Hexin Liu, Xiangyu Zhang +7
The speech tokenizer plays a crucial role in recent speech tasks, generally serving as a bridge between speech signals and language models. While low-frame-rate codecs are widely e…
cs.CL2024
BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference
Junqi Zhao, Zhijin Fang, Shu Li +2
Large language models (LLMs) are essential in natural language processing but often struggle with inference speed and computational efficiency, limiting real-time deployment. The k…